Function conv2d

digital_recognition_cnn.py:28–29 · view source on GitHub ↗

(x, W)

Source from the content-addressed store, hash-verified

26
27	# 卷积采用1步长，0边距，保证输入输出大小相同
28	def conv2d(x, W):
29	return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
30
31	# 池化采用2×2模板
32	def max_pool_2x2(x):

digital_recognition_cnn.pyFile · 0.85

no outgoing calls

no test coverage detected